Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification

PATTERN RECOGNITION

卷:48

Article

Zuo, Zhen¹  Wang, Gang^1,2  Shuai, Bing¹  Zhao, Lifan¹  Yang, Qingxiong³ 

[1] Nanyang Technol Univ, Singapore 639798, Singapore

[2] Adv Digital Sci Ctr, Singapore, Singapore

[3] City Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China

关键词: Deep feature learning;    Information sharing;    Discriminative training;    Scene image classification;   

DOI  :  10.1016/j.patcog.2015.02.003

来源: Elsevier

【 摘 要 】

In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL). DDSFL aims to hierarchically learn feature transformation filter banks to transform raw pixel image patches to features. The learned filter banks are expected to (1) encode common visual patterns of a flexible number of categories; (2) encode discriminative information; and (3) hierarchically extract patterns at different visual levels. Particularly, in each single layer of DDSFL, shareable filters are jointly learned for classes which share the similar patterns. Discriminative power of the filters is achieved by enforcing the features from the same category to be close, while features from different categories to be far away from each other. Furthermore, we also propose two exemplar selection methods to iteratively select training data for more efficient and effective learning. Based on the experimental results, DDSFL can achieve very promising performance, and it also shows great complementary effect to the state-of-the-art Caffe features. (C) 2015 Elsevier Ltd. All rights reserved.

【 授权许可】

Free